KETOS: Clinical decision support and machine learning as a service – A training and deployment platform based on Docker, OMOP-CDM, and FHIR Web Services

Abstract

Background and objective To take full advantage of decision support, machine learning, and patient-level prediction models, it is important that models are not only created, but also deployed in a clinical setting. The KETOS platform demonstrated in this work implements a tool for researchers allowing them to perform statistical analyses and deploy resulting models in a secure environment.

Federated Learning for Healthcare Informatics

“…Federated learning is a viable method to connect EHR data from medical institutions, allowing them to share their experiences, and not their data, with a guarantee of privacy [9,25,34,45,65,82]. In these scenarios, the performance of ML model will be significantly improved by the iterative improvements of learning from large and diverse medical data sets.…”

A Review of AI and Data Science Support for Cancer Management

“…Several of the reviewed papers highlight the need to integrate data from different organizations and systems to allow creating a big-data cohort, in terms of volume and variety of data. Such cohorts could be analyzed statistically [46], can allow clinical study data to be searched and compared [47], or can be used to create more accurate predictive models using machine learning methods [46][48] [49]. Other works focus on the need to apply generic models of clinical decision support onto patient data in order to generate patient-specific recommendations [50,51].…”

“…Indeed, several of the data integration systems that we have reviewed rely either on simple HL7 messages [53] or on the HL7 Fast Healthcare Interoperability Resources (FHIR) standard [46,50,54] to provide semantics to the data that is integrated and allow standardized access to it. In some works, the databases that are accessed via FHIR-APIs, already provide clinical semantics that are richer than simple storage of medical terminology codes.…”

“…The data integration approaches from recent years use a combination of both approaches. Several papers [46][47][48][58][59][60] present ETL database functions that allow pulling data from a source database and placing it into a target database. The first three of these papers define manual processes by which local sites define mappings between source data elements (SDE) to a set of needed common data elements (CDE).…”

“…Data integration should include extract, transform, load (ETL) functions that allow pulling data from a source database (e.g., hospital information system) and storing it in a target database. c. The ETL process can benefit from basing the target database on the Observational Medical Outcomes Partnership (OMOP) common data model (CDM), as in KETOS [46].. OMOP provides services (based on R) to perform distributed analysis of data based on the OMOP semantics. It will help researchers to compare their data and results.…”